Upper Approximation Bounds for Neural Oscillators
By: Zifeng Huang , Konstantin M. Zuev , Yong Xia and more
Potential Business Impact:
Makes AI learn from time-based patterns better.
Neural oscillators, originating from the second-order ordinary differential equations (ODEs), have demonstrated competitive performance in stably learning causal mappings between long-term sequences or continuous temporal functions. However, theoretically quantifying the capacities of their neural network architectures remains a significant challenge. In this study, the neural oscillator consisting of a second-order ODE followed by a multilayer perceptron (MLP) is considered. Its upper approximation bound for approximating causal and uniformly continuous operators between continuous temporal function spaces and that for approximating uniformly asymptotically incrementally stable second-order dynamical systems are derived. The established proof method of the approximation bound for approximating the causal continuous operators can also be directly applied to state-space models consisting of a linear time-continuous complex recurrent neural network followed by an MLP. Theoretical results reveal that the approximation error of the neural oscillator for approximating the second-order dynamical systems scales polynomially with the reciprocals of the widths of two utilized MLPs, thus mitigating the curse of parametric complexity. The decay rates of two established approximation error bounds are validated through two numerical cases. These results provide a robust theoretical foundation for the effective application of the neural oscillator in science and engineering.
Similar Papers
Generalization Bound for a General Class of Neural Ordinary Differential Equations
Machine Learning (CS)
Helps smart computer programs learn better.
Neural solver for sixth-order ordinary differential equations
Numerical Analysis
Teaches computers to solve hard math problems.
Neural Networks for Bayesian Inverse Problems Governed by a Nonlinear ODE
Numerical Analysis
Teaches computers to guess hidden science rules.